Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    any superpower or job

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    مو
    0.53
    тинен
    0.48
    ップ
    0.47
     অধ্য
    0.47
    プーン
    0.46
    安
    0.46
     persones
    0.46
    ',)
    0.46
    रों
    0.45
    )：
    0.45
    POSITIVE LOGITS
    lege
    0.43
    quel
    0.43
    flush
    0.42
    ent
    0.42
    self
    0.42
     dungeon
    0.42
     mujhe
    0.42
    flat
    0.42
     triangular
    0.42
     ruhig
    0.42
    Act Density 0.001%

    No Known Activations